Does it include MLOps best practices?

Absolutely. It covers essentials like data versioning (DVC), experiment tracking with MLflow, model monitoring for drift detection, and CI/CD automation.

What methodology does the Data Analyst skill follow?

It follows the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework, covering business understanding, data preparation, modeling, evaluation, and deployment.

Which Python libraries are supported by this skill?

The skill is designed to work with industry-standard tools including pandas and numpy for processing, scikit-learn for statistics, and matplotlib, seaborn, or plotly for visualization.

Can this skill help with machine learning model evaluation?

Yes, it provides specific metrics and methods for evaluation, including AUC-ROC for classification, RMSE for regression, and various cross-validation techniques like Stratified K-Fold.

Systematic Data Analyst

Name: Systematic Data Analyst
Author: dobachi

bydobachi

0•

데이터 과학 및 ML

Performs end-to-end data science workflows using the CRISP-DM framework to deliver statistical insights, visualizations, and machine learning models.

The Systematic Data Analyst skill transforms Claude into a high-level data science partner that adheres to industry-standard methodologies. It provides a structured approach to the entire data lifecycle—from business requirement definition and exploratory data analysis (EDA) to feature engineering and model deployment. By integrating statistical rigor with modern machine learning practices, this skill helps users navigate complex datasets, identify quality issues, select optimal algorithms, and generate professional reports that drive data-informed decision-making.

주요 기능

01Selection guide for statistical methods and hypothesis testing

02Machine learning reference for supervised and unsupervised algorithm implementation

03Visualization mapping for comparison, trends, composition, and correlation

040 GitHub stars

05Comprehensive EDA toolset including data profiling and quality checklists

06CRISP-DM compliant analysis framework for systematic project execution

사용 사례

01Building and evaluating predictive models using XGBoost, LightGBM, or Transformers

02Executing deep-dive exploratory data analysis on raw business datasets

03Automating data cleaning and feature engineering pipelines for production-ready analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add dobachi/claude-skills-marketplace data-analyst

For use in Claude.ai and ChatGPT

주요 기능

01Selection guide for statistical methods and hypothesis testing

02Machine learning reference for supervised and unsupervised algorithm implementation

03Visualization mapping for comparison, trends, composition, and correlation

040 GitHub stars

05Comprehensive EDA toolset including data profiling and quality checklists

06CRISP-DM compliant analysis framework for systematic project execution

사용 사례

01Building and evaluating predictive models using XGBoost, LightGBM, or Transformers

02Executing deep-dive exploratory data analysis on raw business datasets

03Automating data cleaning and feature engineering pipelines for production-ready analysis

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add dobachi/claude-skills-marketplace data-analyst

For use in Claude.ai and ChatGPT